Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 May 17;11(5):893.
doi: 10.3390/diagnostics11050893.

Detection and Severity Classification of COVID-19 in CT Images Using Deep Learning

Yazan Qiblawey  1 , Anas Tahir  1 , Muhammad E H Chowdhury  1 , Amith Khandakar  1 , Serkan Kiranyaz  1 , Tawsifur Rahman  1 , Nabil Ibtehaz  2 , Sakib Mahmud  1 , Somaya Al Maadeed  3 , Farayi Musharavati  4 , Mohamed Arselene Ayari  5
Affiliations

Detection and Severity Classification of COVID-19 in CT Images Using Deep Learning

Yazan Qiblawey et al. Diagnostics (Basel). .

Abstract

Detecting COVID-19 at an early stage is essential to reduce the mortality risk of the patients. In this study, a cascaded system is proposed to segment the lung, detect, localize, and quantify COVID-19 infections from computed tomography images. An extensive set of experiments were performed using Encoder-Decoder Convolutional Neural Networks (ED-CNNs), UNet, and Feature Pyramid Network (FPN), with different backbone (encoder) structures using the variants of DenseNet and ResNet. The conducted experiments for lung region segmentation showed a Dice Similarity Coefficient (DSC) of 97.19% and Intersection over Union (IoU) of 95.10% using U-Net model with the DenseNet 161 encoder. Furthermore, the proposed system achieved an elegant performance for COVID-19 infection segmentation with a DSC of 94.13% and IoU of 91.85% using the FPN with DenseNet201 encoder. The proposed system can reliably localize infections of various shapes and sizes, especially small infection regions, which are rarely considered in recent studies. Moreover, the proposed system achieved high COVID-19 detection performance with 99.64% sensitivity and 98.72% specificity. Finally, the system was able to discriminate between different severity levels of COVID-19 infection over a dataset of 1110 subjects with sensitivity values of 98.3%, 71.2%, 77.8%, and 100% for mild, moderate, severe, and critical, respectively.

Keywords: COVID-19; deep learning; lesion segmentation; lung segmentation; severity classification.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Schematic representation of the pipeline of the proposed COVID-19 recognition system.
Figure 2
Figure 2
Sample of processed and unprocessed CT images used in this work.
Figure 3
Figure 3
Proposed approach to calculate the infection percentage for CT image.
Figure 4
Figure 4
CT image (1st row), ground truth (2nd row), and the segmentation masks of the top three networks (rows 3–5).
Figure 5
Figure 5
CT image (1st row), ground truth (2nd row), and the lesion segmentation of the top three networks (rows 3–5).
Figure 6
Figure 6
CT image (1st row), ground truth (2nd row), and the lesion segmentation of the best network (row 3) is shown in red.
Figure 7
Figure 7
Detection of lung and lesion for external validation (Lung segmentation: green, infection: red).
Figure 8
Figure 8
Confusion matrix for CT severity classification of the CT volumes of MosMedData Dataset.
Figure 9
Figure 9
The proposed 3D lung models from different views whilst the infection area is marked in red.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. World Health Organization . Weekly Epidemiological Update on COVID-19, 15 December 2020. World Health Organization; Geneva, Switzerland: 2020. p. 21.
    1. Craw P., Balachandran W. Isothermal nucleic acid amplification technologies for point-of-care diagnostics: A critical review. Lab Chip. 2012;12:2469–2486. doi: 10.1039/c2lc40100b. - DOI - PubMed
    1. Corman V.M., Landt O., Kaiser M., Molenkamp R., Meijer A., Chu D.K., Bleicker T., Brünink S., Schneider J., Schmidt M.L., et al. Detection of 2019 novel coronavirus (2019-nCoV) by real-time RT-PCR. Eurosurveillance. 2020;25:2000045. doi: 10.2807/1560-7917.ES.2020.25.3.2000045. - DOI - PMC - PubMed
    1. Kakodkar P., Kaka N., Baig M.N. A Comprehensive Literature Review on the Clinical Presentation, and Management of the Pandemic Coronavirus Disease 2019 (COVID-19) Cureus. 2020;12:e7560. doi: 10.7759/cureus.7560. - DOI - PMC - PubMed
    1. Rubin G.D., Ryerson C.J., Haramati L.B., Sverzellati N., Kanne J.P., Raoof S., Schluger N.W., Volpi A., Yim J.-J., Martin I.B.K., et al. The Role of Chest Imaging in Patient Management during the COVID-19 Pandemic: A Multinational Consensus Statement from the Fleischner Society. Radiology. 2020;296:172–180. doi: 10.1148/radiol.2020201365. - DOI - PMC - PubMed

LinkOut - more resources